[Qemu-devel] [PATCH v8 0/4] The intro of QEMU block I/O throttling

[Qemu-devel] [PATCH v8 0/4] The intro of QEMU block I/O throttling

[Zhi Yong Wu]

The main goal of the patch is to effectively cap the disk I/O speed or counts of one single VM.It is only one draft, so it unavoidably has some drawbacks, if you catch them, please let me know.

The patch will mainly introduce one block I/O throttling algorithm, one timer and one block queue for each I/O limits enabled drive.

When a block request is coming in, the throttling algorithm will check if its I/O rate or counts exceed the limits; if yes, then it will enqueue to the block queue; The timer will handle the I/O requests in it.

Some available features follow as below:
(1) global bps limit.
   -drive bps=xxx            in bytes/s
(2) only read bps limit
   -drive bps_rd=xxx         in bytes/s
(3) only write bps limit
   -drive bps_wr=xxx         in bytes/s
(4) global iops limit
   -drive iops=xxx           in ios/s
(5) only read iops limit
   -drive iops_rd=xxx        in ios/s
(6) only write iops limit
   -drive iops_wr=xxx        in ios/s
(7) the combination of some limits.
   -drive bps=xxx,iops=xxx

Known Limitations:
(1) #1 can not coexist with #2, #3
(2) #4 can not coexist with #5, #6
(3) When bps/iops limits are specified to a small value such as 511 bytes/s, this VM will hang up. We are considering how to handle this senario.

Changes since code V7:
  fix the build per patch based on stefan's comments.

Zhi Yong Wu (4):
  block: add the command line support
  block: add the block queue support
  block: add block timer and throttling algorithm
  qmp/hmp: add block_set_io_throttle

 v7: Mainly simply the block queue.
     Adjust codes based on stefan's comments.

 v6: Mainly fix the aio callback issue for block queue.
     Adjust codes based on Ram Pai's comments.

 v5: add qmp/hmp support.
     Adjust the codes based on stefan's comments
     qmp/hmp: add block_set_io_throttle

 v4: fix memory leaking based on ryan's feedback.

 v3: Added the code for extending slice time, and modified the method to compute wait time for the timer.

 v2: The codes V2 for QEMU disk I/O limits.
     Modified the codes mainly based on stefan's comments.

 v1: Submit the codes for QEMU disk I/O limits.
     Only a code draft.


 Makefile.objs     |    2 +-
 block.c           |  331 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 block.h           |    6 +-
 block/blk-queue.c |  184 +++++++++++++++++++++++++++++
 block/blk-queue.h |   59 ++++++++++
 block_int.h       |   30 +++++
 blockdev.c        |   98 ++++++++++++++++
 blockdev.h        |    2 +
 hmp-commands.hx   |   15 +++
 qemu-config.c     |   24 ++++
 qemu-options.hx   |    1 +
 qerror.c          |    4 +
 qerror.h          |    3 +
 qmp-commands.hx   |   52 ++++++++-
 14 files changed, 796 insertions(+), 15 deletions(-)
 create mode 100644 block/blk-queue.c
 create mode 100644 block/blk-queue.h

-- 
1.7.6

[Qemu-devel] [PATCH v8 1/4] block: add the block queue support

[Zhi Yong Wu]

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 Makefile.objs     |    2 +-
 block/blk-queue.c |  184 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-queue.h |   59 +++++++++++++++++
 block_int.h       |   27 ++++++++
 4 files changed, 271 insertions(+), 1 deletions(-)
 create mode 100644 block/blk-queue.c
 create mode 100644 block/blk-queue.h

diff --git a/Makefile.objs b/Makefile.objs
index 26b885b..5dcf456 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -33,7 +33,7 @@ block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vv
 block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-nested-y += qed-check.o
-block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o blk-queue.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
 block-nested-$(CONFIG_POSIX) += raw-posix.o
 block-nested-$(CONFIG_CURL) += curl.o
diff --git a/block/blk-queue.c b/block/blk-queue.c
new file mode 100644
index 0000000..da01fcb
--- /dev/null
+++ b/block/blk-queue.c
@@ -0,0 +1,184 @@
+/*
+ * QEMU System Emulator queue definition for block layer
+ *
+ * Copyright (c) IBM, Corp. 2011
+ *
+ * Authors:
+ *  Zhi Yong Wu  <wuzhy@linux.vnet.ibm.com>
+ *  Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "block_int.h"
+#include "block/blk-queue.h"
+#include "qemu-common.h"
+
+/* The APIs for block request queue on qemu block layer.
+ */
+
+struct BlockQueueAIOCB {
+    BlockDriverAIOCB common;
+    QTAILQ_ENTRY(BlockQueueAIOCB) entry;
+    BlockRequestHandler *handler;
+    BlockDriverAIOCB *real_acb;
+
+    int64_t sector_num;
+    QEMUIOVector *qiov;
+    int nb_sectors;
+};
+
+typedef struct BlockQueueAIOCB BlockQueueAIOCB;
+
+struct BlockQueue {
+    QTAILQ_HEAD(requests, BlockQueueAIOCB) requests;
+    bool flushing;
+};
+
+static void qemu_block_queue_dequeue(BlockQueue *queue,
+                                     BlockQueueAIOCB *request)
+{
+    BlockQueueAIOCB *req;
+
+    assert(queue);
+    while (!QTAILQ_EMPTY(&queue->requests)) {
+        req = QTAILQ_FIRST(&queue->requests);
+        if (req == request) {
+            QTAILQ_REMOVE(&queue->requests, req, entry);
+            break;
+        }
+    }
+}
+
+static void qemu_block_queue_cancel(BlockDriverAIOCB *acb)
+{
+    BlockQueueAIOCB *request = container_of(acb, BlockQueueAIOCB, common);
+    if (request->real_acb) {
+        bdrv_aio_cancel(request->real_acb);
+    } else {
+        assert(request->common.bs->block_queue);
+        qemu_block_queue_dequeue(request->common.bs->block_queue,
+                                 request);
+    }
+
+    qemu_aio_release(request);
+}
+
+static AIOPool block_queue_pool = {
+    .aiocb_size         = sizeof(struct BlockQueueAIOCB),
+    .cancel             = qemu_block_queue_cancel,
+};
+
+BlockQueue *qemu_new_block_queue(void)
+{
+    BlockQueue *queue;
+
+    queue = g_malloc0(sizeof(BlockQueue));
+
+    QTAILQ_INIT(&queue->requests);
+
+    queue->flushing = false;
+
+    return queue;
+}
+
+void qemu_del_block_queue(BlockQueue *queue)
+{
+    BlockQueueAIOCB *request, *next;
+
+    QTAILQ_FOREACH_SAFE(request, &queue->requests, entry, next) {
+        QTAILQ_REMOVE(&queue->requests, request, entry);
+        qemu_aio_release(request);
+    }
+
+    g_free(queue);
+}
+
+BlockDriverAIOCB *qemu_block_queue_enqueue(BlockQueue *queue,
+                        BlockDriverState *bs,
+                        BlockRequestHandler *handler,
+                        int64_t sector_num,
+                        QEMUIOVector *qiov,
+                        int nb_sectors,
+                        BlockDriverCompletionFunc *cb,
+                        void *opaque)
+{
+    BlockDriverAIOCB *acb;
+    BlockQueueAIOCB *request;
+
+    if (queue->flushing) {
+        return NULL;
+    } else {
+        acb = qemu_aio_get(&block_queue_pool, bs,
+                           cb, opaque);
+        request = container_of(acb, BlockQueueAIOCB, common);
+        request->handler       = handler;
+        request->sector_num    = sector_num;
+        request->qiov          = qiov;
+        request->nb_sectors    = nb_sectors;
+        request->real_acb      = NULL;
+        QTAILQ_INSERT_TAIL(&queue->requests, request, entry);
+    }
+
+    return acb;
+}
+
+static int qemu_block_queue_handler(BlockQueueAIOCB *request)
+{
+    int ret;
+    BlockDriverAIOCB *res;
+
+    res = request->handler(request->common.bs, request->sector_num,
+                           request->qiov, request->nb_sectors,
+                           request->common.cb, request->common.opaque);
+    if (res) {
+        request->real_acb = res;
+    }
+
+    ret = (res == NULL) ? 0 : 1;
+
+    return ret;
+}
+
+void qemu_block_queue_flush(BlockQueue *queue)
+{
+    queue->flushing = true;
+    while (!QTAILQ_EMPTY(&queue->requests)) {
+        BlockQueueAIOCB *request = NULL;
+        int ret = 0;
+
+        request = QTAILQ_FIRST(&queue->requests);
+        QTAILQ_REMOVE(&queue->requests, request, entry);
+
+        ret = qemu_block_queue_handler(request);
+        if (ret == 0) {
+            QTAILQ_INSERT_HEAD(&queue->requests, request, entry);
+            break;
+        }
+
+        qemu_aio_release(request);
+    }
+
+    queue->flushing = false;
+}
+
+bool qemu_block_queue_has_pending(BlockQueue *queue)
+{
+    return !queue->flushing && !QTAILQ_EMPTY(&queue->requests);
+}
diff --git a/block/blk-queue.h b/block/blk-queue.h
new file mode 100644
index 0000000..c1529f7
--- /dev/null
+++ b/block/blk-queue.h
@@ -0,0 +1,59 @@
+/*
+ * QEMU System Emulator queue declaration for block layer
+ *
+ * Copyright (c) IBM, Corp. 2011
+ *
+ * Authors:
+ *  Zhi Yong Wu  <wuzhy@linux.vnet.ibm.com>
+ *  Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_BLOCK_QUEUE_H
+#define QEMU_BLOCK_QUEUE_H
+
+#include "block.h"
+#include "qemu-queue.h"
+
+typedef BlockDriverAIOCB* (BlockRequestHandler) (BlockDriverState *bs,
+                                int64_t sector_num, QEMUIOVector *qiov,
+                                int nb_sectors, BlockDriverCompletionFunc *cb,
+                                void *opaque);
+
+typedef struct BlockQueue BlockQueue;
+
+BlockQueue *qemu_new_block_queue(void);
+
+void qemu_del_block_queue(BlockQueue *queue);
+
+BlockDriverAIOCB *qemu_block_queue_enqueue(BlockQueue *queue,
+                        BlockDriverState *bs,
+                        BlockRequestHandler *handler,
+                        int64_t sector_num,
+                        QEMUIOVector *qiov,
+                        int nb_sectors,
+                        BlockDriverCompletionFunc *cb,
+                        void *opaque);
+
+void qemu_block_queue_flush(BlockQueue *queue);
+
+bool qemu_block_queue_has_pending(BlockQueue *queue);
+
+#endif /* QEMU_BLOCK_QUEUE_H */
diff --git a/block_int.h b/block_int.h
index 8a72b80..201e635 100644
--- a/block_int.h
+++ b/block_int.h
@@ -29,10 +29,18 @@
 #include "qemu-queue.h"
 #include "qemu-coroutine.h"
 #include "qemu-timer.h"
+#include "block/blk-queue.h"
 
 #define BLOCK_FLAG_ENCRYPT	1
 #define BLOCK_FLAG_COMPAT6	4
 
+#define BLOCK_IO_LIMIT_READ     0
+#define BLOCK_IO_LIMIT_WRITE    1
+#define BLOCK_IO_LIMIT_TOTAL    2
+
+#define BLOCK_IO_SLICE_TIME     100000000
+#define NANOSECONDS_PER_SECOND  1000000000.0
+
 #define BLOCK_OPT_SIZE          "size"
 #define BLOCK_OPT_ENCRYPT       "encryption"
 #define BLOCK_OPT_COMPAT6       "compat6"
@@ -49,6 +57,16 @@ typedef struct AIOPool {
     BlockDriverAIOCB *free_aiocb;
 } AIOPool;
 
+typedef struct BlockIOLimit {
+    uint64_t bps[3];
+    uint64_t iops[3];
+} BlockIOLimit;
+
+typedef struct BlockIODisp {
+    uint64_t bytes[2];
+    uint64_t ios[2];
+} BlockIODisp;
+
 struct BlockDriver {
     const char *format_name;
     int instance_size;
@@ -184,6 +202,15 @@ struct BlockDriverState {
 
     void *sync_aiocb;
 
+    /* the time for latest disk I/O */
+    int64_t slice_start;
+    int64_t slice_end;
+    BlockIOLimit io_limits;
+    BlockIODisp  io_disps;
+    BlockQueue   *block_queue;
+    QEMUTimer    *block_timer;
+    bool         io_limits_enabled;
+
     /* I/O stats (display with "info blockstats"). */
     uint64_t nr_bytes[BDRV_MAX_IOTYPE];
     uint64_t nr_ops[BDRV_MAX_IOTYPE];
-- 
1.7.6

[Qemu-devel] [PATCH v8 2/4] block: add the command line support

[Zhi Yong Wu]

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 block.c         |   59 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 block.h         |    5 ++++
 block_int.h     |    3 ++
 blockdev.c      |   29 +++++++++++++++++++++++++++
 qemu-config.c   |   24 ++++++++++++++++++++++
 qemu-options.hx |    1 +
 6 files changed, 121 insertions(+), 0 deletions(-)

diff --git a/block.c b/block.c
index 43742b7..cd75183 100644
--- a/block.c
+++ b/block.c
@@ -104,6 +104,57 @@ int is_windows_drive(const char *filename)
 }
 #endif
 
+/* throttling disk I/O limits */
+void bdrv_io_limits_disable(BlockDriverState *bs)
+{
+    bs->io_limits_enabled = false;
+
+    if (bs->block_queue) {
+        qemu_block_queue_flush(bs->block_queue);
+        qemu_del_block_queue(bs->block_queue);
+        bs->block_queue = NULL;
+    }
+
+    if (bs->block_timer) {
+        qemu_del_timer(bs->block_timer);
+        qemu_free_timer(bs->block_timer);
+        bs->block_timer     = NULL;
+    }
+
+    bs->slice_start = 0;
+
+    bs->slice_end   = 0;
+}
+
+static void bdrv_block_timer(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    BlockQueue *queue    = bs->block_queue;
+
+    qemu_block_queue_flush(queue);
+}
+
+void bdrv_io_limits_enable(BlockDriverState *bs)
+{
+    bs->block_queue = qemu_new_block_queue();
+    bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
+
+    bs->slice_start = qemu_get_clock_ns(vm_clock);
+
+    bs->slice_end   = bs->slice_start + BLOCK_IO_SLICE_TIME;
+}
+
+bool bdrv_io_limits_enabled(BlockDriverState *bs)
+{
+    BlockIOLimit *io_limits = &bs->io_limits;
+    return io_limits->bps[BLOCK_IO_LIMIT_READ]
+         || io_limits->bps[BLOCK_IO_LIMIT_WRITE]
+         || io_limits->bps[BLOCK_IO_LIMIT_TOTAL]
+         || io_limits->iops[BLOCK_IO_LIMIT_READ]
+         || io_limits->iops[BLOCK_IO_LIMIT_WRITE]
+         || io_limits->iops[BLOCK_IO_LIMIT_TOTAL];
+}
+
 /* check if the path starts with "<protocol>:" */
 static int path_has_protocol(const char *path)
 {
@@ -1453,6 +1504,14 @@ void bdrv_get_geometry_hint(BlockDriverState *bs,
     *psecs = bs->secs;
 }
 
+/* throttling disk io limits */
+void bdrv_set_io_limits(BlockDriverState *bs,
+                            BlockIOLimit *io_limits)
+{
+    bs->io_limits = *io_limits;
+    bs->io_limits_enabled = bdrv_io_limits_enabled(bs);
+}
+
 /* Recognize floppy formats */
 typedef struct FDFormat {
     FDriveType drive;
diff --git a/block.h b/block.h
index 3ac0b94..a3e69db 100644
--- a/block.h
+++ b/block.h
@@ -58,6 +58,11 @@ void bdrv_info(Monitor *mon, QObject **ret_data);
 void bdrv_stats_print(Monitor *mon, const QObject *data);
 void bdrv_info_stats(Monitor *mon, QObject **ret_data);
 
+/* disk I/O throttling */
+void bdrv_io_limits_enable(BlockDriverState *bs);
+void bdrv_io_limits_disable(BlockDriverState *bs);
+bool bdrv_io_limits_enabled(BlockDriverState *bs);
+
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
 BlockDriver *bdrv_find_protocol(const char *filename);
diff --git a/block_int.h b/block_int.h
index 201e635..368c776 100644
--- a/block_int.h
+++ b/block_int.h
@@ -257,6 +257,9 @@ void qemu_aio_release(void *p);
 
 void *qemu_blockalign(BlockDriverState *bs, size_t size);
 
+void bdrv_set_io_limits(BlockDriverState *bs,
+                            BlockIOLimit *io_limits);
+
 #ifdef _WIN32
 int is_windows_drive(const char *filename);
 #endif
diff --git a/blockdev.c b/blockdev.c
index 2602591..619ae9f 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -236,6 +236,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     int on_read_error, on_write_error;
     const char *devaddr;
     DriveInfo *dinfo;
+    BlockIOLimit io_limits;
     int snapshot = 0;
     int ret;
 
@@ -354,6 +355,31 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         }
     }
 
+    /* disk I/O throttling */
+    io_limits.bps[BLOCK_IO_LIMIT_TOTAL]  =
+                           qemu_opt_get_number(opts, "bps", 0);
+    io_limits.bps[BLOCK_IO_LIMIT_READ]   =
+                           qemu_opt_get_number(opts, "bps_rd", 0);
+    io_limits.bps[BLOCK_IO_LIMIT_WRITE]  =
+                           qemu_opt_get_number(opts, "bps_wr", 0);
+    io_limits.iops[BLOCK_IO_LIMIT_TOTAL] =
+                           qemu_opt_get_number(opts, "iops", 0);
+    io_limits.iops[BLOCK_IO_LIMIT_READ]  =
+                           qemu_opt_get_number(opts, "iops_rd", 0);
+    io_limits.iops[BLOCK_IO_LIMIT_WRITE] =
+                           qemu_opt_get_number(opts, "iops_wr", 0);
+
+    if (((io_limits.bps[BLOCK_IO_LIMIT_TOTAL] != 0)
+            && ((io_limits.bps[BLOCK_IO_LIMIT_READ] != 0)
+            || (io_limits.bps[BLOCK_IO_LIMIT_WRITE] != 0)))
+            || ((io_limits.iops[BLOCK_IO_LIMIT_TOTAL] != 0)
+            && ((io_limits.iops[BLOCK_IO_LIMIT_READ] != 0)
+            || (io_limits.iops[BLOCK_IO_LIMIT_WRITE] != 0)))) {
+        error_report("bps(iops) and bps_rd/bps_wr(iops_rd/iops_wr)"
+                     "cannot be used at the same time");
+        return NULL;
+    }
+
     on_write_error = BLOCK_ERR_STOP_ENOSPC;
     if ((buf = qemu_opt_get(opts, "werror")) != NULL) {
         if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO && type != IF_NONE) {
@@ -461,6 +487,9 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     bdrv_set_on_error(dinfo->bdrv, on_read_error, on_write_error);
 
+    /* disk I/O throttling */
+    bdrv_set_io_limits(dinfo->bdrv, &io_limits);
+
     switch(type) {
     case IF_IDE:
     case IF_SCSI:
diff --git a/qemu-config.c b/qemu-config.c
index 7a7854f..405e587 100644
--- a/qemu-config.c
+++ b/qemu-config.c
@@ -85,6 +85,30 @@ static QemuOptsList qemu_drive_opts = {
             .name = "readonly",
             .type = QEMU_OPT_BOOL,
             .help = "open drive file as read-only",
+        },{
+            .name = "iops",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit total I/O operations per second",
+        },{
+            .name = "iops_rd",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit read operations per second",
+        },{
+            .name = "iops_wr",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit write operations per second",
+        },{
+            .name = "bps",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit total bytes per second",
+        },{
+            .name = "bps_rd",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit read bytes per second",
+        },{
+            .name = "bps_wr",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit write bytes per second",
         },
         { /* end of list */ }
     },
diff --git a/qemu-options.hx b/qemu-options.hx
index 659ecb2..2e42c5c 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -136,6 +136,7 @@ DEF("drive", HAS_ARG, QEMU_OPTION_drive,
     "       [,cache=writethrough|writeback|none|directsync|unsafe][,format=f]\n"
     "       [,serial=s][,addr=A][,id=name][,aio=threads|native]\n"
     "       [,readonly=on|off]\n"
+    "       [[,bps=b]|[[,bps_rd=r][,bps_wr=w]]][[,iops=i]|[[,iops_rd=r][,iops_wr=w]]\n"
     "                use 'file' as a drive image\n", QEMU_ARCH_ALL)
 STEXI
 @item -drive @var{option}[,@var{option}[,@var{option}[,...]]]
-- 
1.7.6

[Qemu-devel] [PATCH v8 0/4] The intro of QEMU block I/O throttling

[Zhi Yong Wu]

The main goal of the patch is to effectively cap the disk I/O speed or counts of one single VM.It is only one draft, so it unavoidably has some drawbacks, if you catch them, please let me know.

The patch will mainly introduce one block I/O throttling algorithm, one timer and one block queue for each I/O limits enabled drive.

When a block request is coming in, the throttling algorithm will check if its I/O rate or counts exceed the limits; if yes, then it will enqueue to the block queue; The timer will handle the I/O requests in it.

Some available features follow as below:
(1) global bps limit.
   -drive bps=xxx            in bytes/s
(2) only read bps limit
   -drive bps_rd=xxx         in bytes/s
(3) only write bps limit
   -drive bps_wr=xxx         in bytes/s
(4) global iops limit
   -drive iops=xxx           in ios/s
(5) only read iops limit
   -drive iops_rd=xxx        in ios/s
(6) only write iops limit
   -drive iops_wr=xxx        in ios/s
(7) the combination of some limits.
   -drive bps=xxx,iops=xxx

Known Limitations:
(1) #1 can not coexist with #2, #3
(2) #4 can not coexist with #5, #6
(3) When bps/iops limits are specified to a small value such as 511 bytes/s, this VM will hang up. We are considering how to handle this senario.

Changes since code V7:
  fix the build per patch based on stefan's comments.

Zhi Yong Wu (4):
  block: add the command line support
  block: add the block queue support
  block: add block timer and throttling algorithm
  qmp/hmp: add block_set_io_throttle

 v7: Mainly simply the block queue.
     Adjust codes based on stefan's comments.

 v6: Mainly fix the aio callback issue for block queue.
     Adjust codes based on Ram Pai's comments.

 v5: add qmp/hmp support.
     Adjust the codes based on stefan's comments
     qmp/hmp: add block_set_io_throttle

 v4: fix memory leaking based on ryan's feedback.

 v3: Added the code for extending slice time, and modified the method to compute wait time for the timer.

 v2: The codes V2 for QEMU disk I/O limits.
     Modified the codes mainly based on stefan's comments.

 v1: Submit the codes for QEMU disk I/O limits.
     Only a code draft.


 Makefile.objs     |    2 +-
 block.c           |  344 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 block.h           |    6 +-
 block/blk-queue.c |  201 +++++++++++++++++++++++++++++++
 block/blk-queue.h |   59 +++++++++
 block_int.h       |   30 +++++
 blockdev.c        |   98 +++++++++++++++
 blockdev.h        |    2 +
 hmp-commands.hx   |   15 +++
 qemu-config.c     |   24 ++++
 qemu-options.hx   |    1 +
 qerror.c          |    4 +
 qerror.h          |    3 +
 qmp-commands.hx   |   52 ++++++++-
 14 files changed, 825 insertions(+), 16 deletions(-)
 create mode 100644 block/blk-queue.c
 create mode 100644 block/blk-queue.h

-- 
1.7.6